A method of providing product information and an electronic device

Abstract

This application discloses a method and electronic device for providing product information. The method includes: receiving a product information search request and providing a first user interface; responding to the product information search request, generating generative object content corresponding to the product information search request based on a pre-trained artificial intelligence model, and displaying the generative object content in the first user interface; the generative object content includes product search results and interactive shelf labels; wherein the product search results are displayed according to a product shelf structure; receiving user operations through the interactive shelf labels, and performing corresponding operation actions in response to the user operations to refresh or change part or all of the product information search results, or to provide new search content after triggering a new search. This method can improve the richness of product search results, the relevance to user needs, and the interactivity of the search process.

Description

Technical Field

[0001] This application relates to the field of information processing technology, and in particular to a method and electronic device for providing product information. Background Technology

[0002] The widespread application of commodity information service systems has brought convenience to users' shopping activities. With the continuous development of these systems, their commodity information data and coverage have reached a much larger scale. To find products or services that meet users' needs from a vast amount of commodity information, the commodity information search function provided by these systems is indispensable. Traditional commodity search functions include keyword-based searches. For example, users can input keywords representing their current needs, such as product or category. After receiving the user's search keywords, the commodity information service system can perform a series of query-related operations. This includes understanding and identifying the search keywords, searching and recalling candidate products related to the search keywords in a large commodity information database, and sorting candidate products based on characteristics such as product features and user characteristics. Finally, the search results can be provided to the user in a certain order to meet their commodity information search needs. With the development of product information search technology in product information service systems, various efficient algorithms have been applied to all stages of the product information query process. Product information query technology has evolved from rule-based keyword matching to a more complex technology system centered on data and artificial intelligence algorithm models. New trends have emerged, such as end-to-end deep learning, multimodal search, and conversational search. These advancements have improved the efficiency and accuracy of product information searches, better meeting the demands for large-scale and personalized searches. However, existing product information search still has areas for improvement, such as the flexibility of how search results are presented and the interaction methods with users when providing search results. Summary of the Invention

[0003] This application provides a method and electronic device for providing product information, which can improve the richness of product search results, the degree of relevance to user needs, and the interactivity of the search process.

[0004] This application provides the following solution: A method for providing product information includes: Receive product information search requests and provide a first user interface; In response to the product information search request, based on a pre-trained artificial intelligence model, generative object content corresponding to the product information search request is generated and displayed in the first user interface; the generative object content includes product search results and interactive shelf labels; wherein, the product search results are displayed according to a product shelf structure; The interactive shelf label receives user input and responds to the user input by performing corresponding actions to refresh or change part or all of the product information search results, or to provide new search content after triggering a new search.

[0005] The interactive shelf label includes a first interactive label; The step of receiving user input via the interactive shelf label and performing corresponding actions in response to the user input includes: The system receives user actions via the first interactive tag, responds to the user actions, regenerates generative object content based on the tag information corresponding to the first interactive tag, and provides the regenerated generative object content.

[0006] The interactive shelf label includes a second interactive label; The step of receiving user input via the interactive shelf label and performing corresponding actions in response to the user input includes: The system receives user actions via the second interactive label and, in response to the user actions, updates the product search results displayed in a shelf-like structure based on the label information corresponding to the second interactive label.

[0007] The product search results include product information and product category information, wherein one product category information corresponds to one or more product information. The step of updating the product search results displayed according to the product shelf structure based on the tag information corresponding to the second interactive tag includes: The product category information determined by the tag information corresponding to the second interactive tag is inserted into the product category information of the product search results, and the corresponding product information is provided under that category.

[0008] This also includes: The system provides a "Retain Category" option to preserve product category information. When a user operation is received through the "Retain Category" option, the system saves the determined product category information.

[0009] The interactive shelf label includes a third interactive label; The step of receiving user input via the interactive shelf label and performing corresponding actions in response to the user input includes: The system receives user operations via the third interactive tag, responds to the user operations by providing a second user interface, generates corresponding generative object content based on the tag information corresponding to the third interactive tag, and provides the generative object content generated based on the tag information corresponding to the third interactive tag in the second user interface.

[0010] The generative object content provided in the second user interface includes operation options for product information or product category information; the method further includes: Depending on whether the user's operation options for the product information or the operation options for the product category information result in an operation, the product search results in the first user interface are updated when returning to the first user interface, or the tag information corresponding to the third interactive tag is updated.

[0011] The tag information corresponding to the third interactive tag includes: Based on the product information search request, a divergent prompt question is generated using a pre-trained artificial intelligence model.

[0012] The product search results include product category information, which includes one or any combination of the following product category information: Scenario-based product category information; Product category classification information; Recipe category information; Customize product category information.

[0013] The product shelf structure includes card-type information units; The method further includes: The card-type information unit provides a combination of different types of generated content.

[0014] This also includes: A dialog interaction unit is provided in the first user interface or the second user interface; The dialogue interaction unit receives new product information search requests, and based on the received new product information search requests, regenerates generative object content corresponding to the new product information search requests using a pre-trained artificial intelligence model, and refreshes the user interface to provide the regenerated generative object content in the corresponding user interface.

[0015] The generative object content includes text content; the interactive shelf label includes text anchors within the text content.

[0016] An electronic device, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of any of the preceding methods.

[0017] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application enables the provision of a first user interface upon receiving a product information search request; in response to the product information search request, a generative object content corresponding to the product information search request is generated based on a pre-trained artificial intelligence model, and the generative object content is displayed in the first user interface; the generative object content includes product search results and interactive shelf labels, and the product search results are displayed according to a product shelf structure; user operations are received through interactive shelf labels, and corresponding operation actions are performed in response to user operations to refresh or change part or all of the product information search results, or to provide new search content after triggering a new search. This method firstly allows for the generation of generative object content based on a pre-trained artificial intelligence model to provide product search results during product searches. The product information in the search results is included in a product search result structured like a product shelf, presenting rich and structured product search result information, thus improving the richness and readability of the search results. Secondly, the generative object content also includes operable, interactive shelf labels. These labels receive user input and respond to user actions by performing corresponding actions. After an interactive shelf label is manipulated, it generates further actions on the current search results, refreshing or changing part or all of the product search results, or triggering a new search to provide new search content. This satisfies the user's further search interaction needs while browsing the current search results, thereby deepening the granularity of product search needs mining, improving the richness of search results, enhancing the fit between product search results and user needs, and increasing the interactivity of the search process.

[0018] Furthermore, it provides interactive shelf labels of different types and functions. These labels can generate different actions and effects on the current search results in the first user interface. By providing these interactive shelf labels in the search results, users can notice and use the operation options of these labels according to their actual needs during the search results process. This heuristically guides users to obtain search results that better meet their different needs during the product search process, further enriching the content of search results and increasing the interactivity of the product search process.

[0019] Of course, any product implementing this application does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of the method provided in the embodiments of this application; Figure 2 This is a schematic diagram of the first application provided in the embodiments of this application; Figure 3 This is a schematic diagram of the second application provided in the embodiments of this application; Figure 4 This is a schematic diagram of a third application provided in the embodiments of this application; Figure 5 This is a schematic diagram of the fourth application provided in the embodiments of this application; Figure 6 This is a schematic diagram of the fifth application provided in the embodiments of this application; Figure 7 This is a schematic diagram of the device provided in the embodiments of this application; Figure 8 This is a schematic diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0023] With the deepening application of artificial intelligence (AI) algorithms in the field of commodity information services, they have played a significant role at multiple nodes in the commodity service chain, improving the service efficiency of commodity information service platforms for users, including the implementation of commodity information search services. In existing technologies, the application of AI algorithms has improved the efficiency and accuracy of commodity information search services to some extent. For example, it has enabled step-by-step assistance in uncovering users' search needs through dialogue guidance, making the final search results closer to users' actual needs. However, existing technologies still need further improvement in terms of the granularity of user needs, the richness of search results, and the interactivity of the search process.

[0024] This application provides a method for providing product information, which can be applied to a product information service platform. Specifically, it can be applied to a product information search application or process provided by the product information service platform. This method provides generative object content based on a pre-trained artificial intelligence model and directly presents the generative object content, including product information search results, in a product shelf-like structure within the user interface carrying the search results. This improves the richness of product information search results in terms of both content and display structure. The product search results displayed in the product shelf-like structure can directly provide operation options for the products, allowing users to directly operate on the products, such as viewing details, adding to cart, or adding to favorites, thus improving the ease of use of product information search results. Furthermore, in the generative search... The results also provide interactive shelf labels. When these labels are interacted with, corresponding actions can be performed, influencing the overall or partial content of the current search results. Different labels allow for different types of actions, thus enhancing the interactivity of the product information search process. Furthermore, interactive shelf labels can come in different types, each corresponding to different actions, such as refreshing or changing part or all of the product information search results, or triggering a new search and providing new search content. This satisfies users' diverse needs at different levels and in different aspects during the product information search process, increasing the interactivity of the search process while also improving the richness of the search results and their relevance to users' actual needs.

[0025] The specific technical solutions provided in the embodiments of this application will be described in detail below.

[0026] First, this application provides a method for providing product information, please refer to... Figure 1 The flowchart is for the method provided in the embodiments of this application, such as... Figure 1 As shown, the method may include the following steps: S101: Receives product information search requests and provides a first user interface; This application provides a method for providing product information, which can provide product information search results based on a pre-trained artificial intelligence model. The product information search request can be a request sent to a product information service platform, which can use the artificial intelligence model to assist or execute the product information search process. The product information search request can come from different entry channels. For example, the operation entry point for the product information search request can be provided in different functional pages of the client APP application provided by the platform, such as the APP main page, search entry page, search activation page, etc. Upon receiving the product information search request, a first user interface can be provided. The first user interface can be displayed in the client APP and can be a page used to carry or display the search results content corresponding to the product information search request. In this application embodiment, it is mainly used to display the generative object content generated by the pre-trained artificial intelligence model corresponding to the current product information search request, thereby providing product information search results in the form of generative object content. The generative object content generated by the artificial intelligence model can be used as a search result or a part of the search results; that is, at least part of the search results can be generated based on a pre-set artificial intelligence model.

[0027] S102: In response to the product information search request, based on a pre-trained artificial intelligence model, generative object content corresponding to the product information search request is generated, and the generative object content is displayed in the first user interface; the generative object content includes product search results and interactive shelf labels; wherein, the product search results are displayed according to a product shelf structure; Based on a pre-trained artificial intelligence model, generative object content corresponding to product information search requests is generated, and this generative object content can then be provided in the first user interface. In one implementation, the generative object content may include product search results, which may include product information. Product search results can be displayed in a shelf-like structure, where a shelf-like structure refers to a structured data carrier that carries product information in a product information service. This structure can be displayed in a specific area of ​​the user interface, including multiple product display units or resource slots with a certain structure and organization. Product search results displayed in a shelf-like structure may also include one or more product information items. In another implementation, similar to physical shelves in reality, different products can be categorized and displayed in the user interface. Product search results may include product category information, which can typically be intuitively represented by "category titles," etc. Different categories of products are displayed in different resource slots, such as in different tabs within subcategories.

[0028] Product search results can include product category information, where one product category can correspond to one or more product categories. When product search results include product category information, there can be different types of product category information. Specifically, product category information can include any combination of one or more of the following categories: scenario-based product category information, product category-based product category information, recipe-based product category information, and custom product category information. Scenario-based product category information can be category information reflecting the application scenario of the product category, such as the application scenario of healthy eating; product category-based product category information can be category information reflecting the product category, for example, for milk, whole milk, lactose-free, etc. can be considered product category-based product category information; recipe-based product category information can be, for example, product category information about recipes related to a specific type of ingredient generated from product search results, and this type of product category information can be applied to, for example, food e-commerce service platforms; in addition, user-defined custom product category information can also be included. For various product category information, the first user interface can also provide operable operation options for the corresponding product category information. For example, it can provide operation options such as deleting, unpinning, and updating product category information, so as to realize the corresponding operation of product category information and give users more operational freedom.

[0029] The method provided in this application embodiment can display generative object content, including product information search results, in a product shelf-like structure on the user interface carrying the search results. The generative object content can include rich content formats, such as different types of search result information (text, images, videos, product information, etc.), and the structured display in a product shelf-like structure improves the richness and readability of the product information search results. In another implementation, when generating generative object content corresponding to a product information search request based on an artificial intelligence model, user characteristics and the platform's own category structure can be combined to generate product search results that meet the user's personalized needs. When generating product search results displayed in a product shelf-like structure, the product shelf structure can be determined by shelf description information. That is, during specific generation, shelf description information can be provided to a pre-trained artificial intelligence model, which generates generative object content that meets its structural and quantity requirements based on the shelf description information. Alternatively, in another implementation, generative object content can be generated based on the default configuration of the pre-trained artificial intelligence model.

[0030] Furthermore, the generative object content generated based on the pre-trained artificial intelligence model can also include interactive shelf labels. In the method provided in this application embodiment, interactive shelf labels are different concepts from product category information and have different functions. Product category information typically identifies and indicates different product categories. In the user interface, product category information usually corresponds to the operation of switching between different product categories. The function of interactive shelf labels is to have a deeper impact on the product information search results after receiving user operations. For example, it can refresh or change part or all of the product information search results according to actual needs, trigger new searches and provide new search content, etc., rather than just switching between different types of products. In addition, interactive shelf labels of different types / attributes can also be provided. Depending on the type or attribute of the interactive shelf label, it will have different effects on the page or the page content as product information search results. This part will be further described in detail in the following content. In practical applications, interactive shelf labels can be provided as independent functional units in the interface, or they can be integrated into the product shelf structure for display and provision.

[0031] like Figure 2 This is a schematic diagram illustrating a first application of the method provided in an embodiment of this application. Figure 2 The diagram illustrates a first user interface, which includes generative object content generated by a pre-trained artificial intelligence model and corresponding to the product information search request, serving as search results. For example, it includes generative object content generated based on a search request for the topic "milk." This generative object content specifically includes text-based content about milk (such as product descriptions and purchasing suggestions), interactive shelf labels, and product search results displayed in a shelf-like structure. The pre-trained artificial intelligence model can possess multimodal generation capabilities, thereby generating multiple types of information, such as text, images, and videos. Figure 2 The text 201 shown is as follows; area 202 includes multiple interactive shelf labels that can be used to receive user operations; 203 is a product search result generated by an artificial intelligence model and displayed in a shelf-like structure, including product information 205, and area 204 includes multiple category titles that identify different product category information.

[0032] S103: Receive user operations through the interactive shelf label, and perform corresponding operation actions in response to the user operations to refresh or change part or all of the product information search results, or provide new search content after triggering a new search.

[0033] After providing generative object content in the first user interface, user actions can be received through interactive shelf labels, and corresponding actions can be performed in response to these actions. Generally speaking, the corresponding actions of the interactive shelf labels include actions on search results content. Specifically, these actions can be actions on generative object content generated by an AI model corresponding to the product information search request. Depending on the type or attributes of the interactive shelf label, and the different functions or information it carries, different operations or effects can occur on the user interface itself or the generative object content serving as the product information search results. For example, it can refresh or change part or all of the product information search results, or trigger a new search and provide new search content. The corresponding actions of the interactive shelf labels can also include actions on the page content of the first user interface. For example, depending on the interactive shelf label, these actions can be changes to the entire or partial page content of the first user interface, including refreshing the entire or partial page content, or refreshing the layout of the entire or partial page content, etc. This allows users to meet their further search interaction needs while browsing the current search results. Different types of interactive shelf labels can be generated by pre-trained AI models according to different application purposes. Typically, user actions can be clicking on interactive shelf labels, or other types of actions. Interactive shelf labels can include label information, such as... Figure 2 The interactive shelf labels in area 202 shown include multiple interactive shelf labels with label information such as "nutritional value" and "special populations".

[0034] In one implementation, the interactive shelf label may include a first interactive label. Upon receiving a user action via the first interactive label, and in response to the user action, the content of the generative object can be regenerated based on the label information corresponding to the first interactive label, and the regenerated generative object content can be provided. The regenerated generative object content can be provided in the first user interface, which is equivalent to refreshing the display content of the first user interface. In another implementation, a new user interface can be created, and the regenerated generative object content can be provided in the new user interface. The regenerated generative object content may also include product search results displayed according to a product shelf structure (including product information and product category information), as well as the regenerated interactive shelf label, etc. Examples of application scenarios for this implementation can include: the tag information of the first interactive tag can be relevant to the current search topic, or it can identify other dimensions relative to the current product information classification dimension. For example, when the current product information is classified as "frequently used," the tag information of the first interactive tag can be a classification dimension parallel to "frequently used," such as "health"; or other special combinations of products under the current category, etc. (The current product information classification, for example, could be a classification given by the AI ​​model based on commonly used classification dimensions when there are no special needs). A re-search can be triggered by providing the first interactive tag; that is, when the first interactive tag is operated, the search request can be redefined, and search results can be generated to meet new search needs of the user during the interaction on the current search results page. The task of regenerating search results can also be performed by a pre-trained AI model. The tag information corresponding to the first interactive tag can be relevant to the current search request or search topic, but can indicate other content, such as other classification dimensions, other user needs, etc. In another implementation, the search request can be redefined based on the current search term and the tag information corresponding to the first interactive tag to generate generative object content, and the regenerated generative object content can be provided.

[0035] like Figure 3 This is a second application diagram of the method provided in the embodiments of this application. Figure 3 This demonstrates how, after a first interactive label is manipulated, the content of a generative object is regenerated based on the label information corresponding to the first interactive label, and provides an example of the regenerated generative object content. For example... Figure 3As shown, 3(a) is the first user interface displaying the current search results. The first user interface displays the search results page corresponding to the current search request, including generative object content corresponding to the current search request generated by a pre-trained artificial intelligence model. This includes text content 310, multiple interactive shelf labels, and product search results displayed in a shelf-like structure. The product search results displayed in a shelf-like structure include product category information 312 and the corresponding products. When the first interactive label 311 is operated, a new generative object content for the product information search results is regenerated based on the corresponding label information. The search results page is refreshed based on the newly generated content, displaying the page shown in 3(b). In this page, the text content changes to text content 320, the interactive shelf labels change to the newly generated interactive shelf labels shown in area 321, and the regenerated product search results are displayed. In the regenerated product search results, the product category information changes to product category information 322.

[0036] In this example, 3(a) provides an example of a search using "milk" as the search term, and the generative object content generated by a pre-trained artificial intelligence model. For example, the text can be a textual description of milk-related products, such as a general search overview, product / category introduction, purchasing advice, etc. For example, the product category information 312 can be a relatively "common" category of "milk" products, such as "whole milk" or "pure milk". When the first interactive tag 311 is operated, for example, if the information corresponding to interactive tag 311 is "health goal", the generative object content of the new product information search results can be regenerated based on the corresponding tag information "health goal" and displayed on the page in 3(b). In this example, compared to the current product category of milk, "health goals" is a category dimension parallel to "frequently used." It is relatively less frequently used but is related to the current search topic or product category, representing search demand for a specific dimension of product category. Providing such a category dimension to users in the form of interactive shelf labels in the search results can prompt and guide users to inspire their search needs. Based on the current search results, it can further explore and meet users' potential search needs, providing search results that better match user needs. At the same time, it enriches the content of search results during the product search process and increases the interactivity of the product search process.

[0037] In another implementation, the interactive shelf label includes a second interactive label. This second interactive label can receive user input and, in response, update the product search results displayed in a shelf-like structure based on the label information corresponding to the second interactive label. The updated product search results can be regenerated by a pre-trained artificial intelligence model, or rearranged based on the product information and category information in the current product search results, as well as the label information corresponding to the second interactive label. Unlike the previous implementation that regenerates generative object content, this implementation only requires a single refresh of the product search results displayed in a shelf-like structure, including refreshing the product information or rearranging existing product information. An example application scenario for this implementation is that the label information of the second interactive label can identify a category result with a parallel status compared to the current product information category. The update of the current product search results can be triggered by providing the second interactive label. The update of the product search results can be regenerated using a pre-trained artificial intelligence model, or determined by rearranging the product information and category information in the current product search results displayed in a shelf-like structure, to meet the user's needs for obtaining product information under different categories or dimensions during interaction with the search results page.

[0038] In this implementation, product search results can include product category information. One product category can correspond to one or more product categories. When updating product search results based on the tag information corresponding to the second interactive tag, the product category information determined by the tag information corresponding to the second interactive tag can be inserted into the current product category information of the product search results. After updating the product search results, the product search results will include the product category information determined by the tag information corresponding to the second interactive tag. Additionally, a category retention option can be provided for the determined product category information, such as a "pin" option. When a user action is received through the category retention option, the determined product category information is saved. The saved product category information can be directly retrieved when the user searches for the same or similar categories again, or it can be used by an artificial intelligence model to further calculate user preferences.

[0039] like Figure 4 This is a schematic diagram illustrating a third application of the method provided in the embodiments of this application. Figure 4 An example is shown where an interactive shelf label includes a second interactive label, which receives user input and updates the product search results displayed on the shelf structure based on the label information corresponding to the second interactive label. For example... Figure 4As shown, 4(a) is the first user interface displaying the current search results. The first user interface displays the search results page corresponding to the current search request, including generative object content generated by a pre-trained artificial intelligence model, including text content 410, multiple interactive shelf labels, and product search results displayed in a shelf-like structure. The product search results include product category information and corresponding product information. When the second interactive label 411 is operated, the product search results displayed in the shelf-like structure are updated according to the corresponding label information. The updated product search results are displayed on page 4(b), where the product category information determined by the label information corresponding to the second interactive label is inserted into the updated product search results, and the corresponding product information is provided.

[0040] In this example, 4(a) provides an example of a search using "milk" as the search term, with a pre-trained artificial intelligence model generating generative object content. For instance, the text in the generative object content could be a description of milk-related products, and the product category information could be a relatively "common" category for "milk" products. When the second interactive tag 411 is manipulated, for example, if the information corresponding to the second interactive tag 411 is "Juanshan Milk," the product search results displayed in the product shelf structure can be updated based on the corresponding tag information "Juanshan Milk." The product category information determined by the tag information "Juanshan Milk" is inserted into the product search results and displayed on the page in 4(b). 422 in 4(b) is a display unit for product category information, which displays information including the inserted product category information.

[0041] Additionally, the text within the content of the generated object can be updated accordingly, for example... Figure 4 The Chinese text content 410 is updated to the text content 420 in 4(b). In a specific implementation, one approach is to generate the text content 420 and include it in the generative object content in 4(a) when generating the generative object content in 4(a). When the second interactive label 411 is operated, the text content can be scrolled to the text paragraph position where the text content 420 is located for display.

[0042] In addition, operation options are provided in the display unit 422, such as Figure 4 The options shown include "Pin" and "Update". The "Pin" option allows you to pin or save the product category information to preserve the relevant product category information.

[0043] In this example, compared to the commonly used categories of milk, "Jersey Milk" is relatively less common, but it is related to the current search topic or product category, representing a search demand for a specific product category. Providing such product category information to users in the form of interactive shelf labels in the product search results can prompt and guide users to inspire their search needs, further explore and satisfy users' potential search needs, obtain search results that better match user needs, enrich the content of search results during the product search process, and increase the interactivity of the product search process.

[0044] In another implementation, the interactive shelf label may include a third interactive label. When a user operation is received through the interactive shelf label, the user operation can be received through the third interactive label. In response to the user operation, a second user interface can be provided. Generative object content is generated based on the label information corresponding to the third interactive label, and this generative object content is provided in the second user interface. In this implementation, the generative object content generated based on the label information of the third interactive label can be provided in the newly created second user interface. For example, the label information of the third interactive label may be interactive content about the current search topic or product category, or it may be knowledge-guided interactive content, such as interactive content in the form of prompts about product knowledge, product category characteristics, etc. When a user operation is received through the third interactive label, the generative object content related to the label information of the third interactive label can be provided by providing a newly created second user interface to meet the user's need to obtain product information such as specific products or categories during interaction with the search results page.

[0045] like Figure 5 This is a fourth application diagram of the method provided in the embodiments of this application. Figure 5 An example of an interactive shelf label including a third interactive label is shown, through which user actions are received to provide generative object content in a second user interface. 5(a) is a first user interface displaying the current search results. The first user interface displays the search results page corresponding to the current search request, including generative object content generated by a pre-trained artificial intelligence model corresponding to the current search request. When the third interactive label 510 is operated, the second user interface shown in 5(b) is provided. The corresponding generative object content is generated based on the label information corresponding to the third interactive label, and this generative object content is provided through the second user interface. For example, 5(b) provides generative object content related to the label information of the third interactive label 510, including image content, text content 510, and search results for product information related to the label information of the third interactive label 510.

[0046] In this example, 5(a) shows a search query using "milk" as the search term, with generative object content generated by a pre-trained AI model, including a third interactive label 510. The label information corresponding to the third interactive label can include divergent prompts generated by the pre-trained AI model based on the product information search request. For example, as shown in 5(a), the label information corresponding to the third interactive label 510 could be something like "Discover: The Special Features of [Brand Name] Milk." This label information can be knowledge-guided interactive content under the current search topic of "milk," specifically about this type of milk, and can inspire users to further understand relevant information or knowledge about this specific type of milk. After the third interactive label 510 is activated, a second user interface as shown in 5(b) is provided, displaying generative object content generated based on the label information corresponding to the third interactive label 510. This includes images related to this type of milk, text describing this type of milk, tables, and corresponding product search results and operation option recommendations.

[0047] In this example, compared to the commonly used categories for milk, the "milk of a certain type" category is relatively less common, but it is related to the current search topic or product category, representing a search demand for a specific product type. Providing such suggestive information to users in the form of interactive shelf labels in the product search results can guide and inspire users to further understand the relevant product knowledge, further explore and satisfy users' potential search needs, obtain search results that better match user needs, enrich the search results content in the product search process, and increase the interactivity of the product search process.

[0048] In another implementation, the generative object content provided in the second user interface may also include product information, as well as user operation options for the product information, or operation options for product category information, for example... Figure 5The second user interface shown in 5(b) includes generative object content that includes operation options for product information, such as adding products to the shopping cart. Similar operation options may include options for purchasing, favorites, etc., or operation options for product category information, such as the "add to shelf" operation option shown in operation option 521. Furthermore, depending on whether an operation is performed on the user's operation options for product information or product category information, the product search results in the product shelf structure of the first user interface can be updated upon returning to the first user interface, or the tag information corresponding to the third interactive label can be updated. For example, when an operation is performed on the user's operation options for product information or product category information, it means that the user has developed an interest in the generative object content provided in the second user interface, or in the related products or product categories. Upon returning to the first user interface, the product search results in the product shelf structure can be updated, for example, by adding the product information or product category information to the product search results of the first user interface. When adding product category information to the product search results of the first user interface, the product category information can be "pinned" to the product search results of the first user interface to save the determined product category information. If the above-mentioned actions do not occur, it means that the user has low interest in the generative object content provided in the second user interface, or in the related products or product categories. In this case, the tag information corresponding to the updated third interaction tag can be updated when returning to the first user interface to provide new heuristic and guiding content, making it easier for the user to obtain other content through the updated third interaction tag.

[0049] In one implementation, in response to a user's product information search request, the generative object content based on a pre-trained artificial intelligence model may further include card-type information units. These card-type information units can be provided and displayed in the product search results and can be used to provide different information, such as a combination of multiple product search results or different types of generated content. The card titles can be displayed as tags at the same level as the product type information to facilitate user switching. The different types of generated content provided in the card-type information units can be generated content of different types with specific relevance. For example, it could be generated content in different formats related to a product type; or, for example, it could be a combination of a recipe-related cooking method and information on different ingredients. The content displayed in the card-type information units can be generated by the pre-trained artificial intelligence model based on search requirements and product relationships, or it can be generated and determined by referring to product display strategies such as whether to display it in the form of card-type information units, or product attributes, such as whether the product in the search results is a cooking ingredient.

[0050] like Figure 6 This is a fifth application illustration of the method provided in the embodiments of this application. Figure 6 Examples of providing and displaying card-type information units in product search results are shown. Example 6(a) provides an example of a search using "fruit" as the search term, with generative object content generated by a pre-trained AI model. In this example's user interface, a card-type display unit 610 is provided, including a combined title, text description, and multiple product information. The card-type display unit corresponds to the card title "Low GI (Glycemic Index)," and the card title is displayed as a label at the same level as the product type information for easy user switching. Example 6(b) provides an example of a search using "eggs" as the search term, with generative object content generated by a pre-trained AI model. In this example's user interface, a card-type display unit 620 is provided, including the recipe name, recipe text description, and search results for the ingredients used. The card-type display unit corresponds to the card title "Egg Recipes," and the card title is displayed as a label at the same level as the product type information for easy user switching. Each card title can include one or more card-type display units as search results. Furthermore, when providing concise information in card-type display units, an operation option can be provided to offer more detailed information. For example, in card-type display unit 610 of 6(a), an operation option 611 for displaying "more" is provided. After this operation option is activated, a new page will be created providing more search results for "low GI" fruits, or knowledge information about low GI fruits, etc. In card-type display unit 620 of 6(b), an operation option 621 for viewing "recipe details" is provided. After this operation option is activated, a new page will be created providing detailed cooking methods for the corresponding recipe, etc. Providing search results in the form of card-type information units within a product shelf structure of generative object content allows for the aggregation of product search results for specific categories, topics, etc., as well as different types of related information, into a single card-type information unit. This provides a more readable modular view, thereby offering richer search result information and interaction methods during the search process. This further explores and satisfies users' potential search needs, enriches the search result content during the product search process, and increases the interactivity of the product search process.

[0051] In addition, a dialog interaction unit may be provided in the first user interface or the second user interface, for example, its form may be... Figure 5The dialogue input box displayed at the bottom of section 5(b) allows for interactive dialogue. This dialogue interaction unit can receive new product information search requests. Based on a pre-trained artificial intelligence model, it regenerates generative object content corresponding to the new search request and refreshes the user interface to display the regenerated generative object content. This allows users to initiate new searches at any time while browsing current search results through the first or second user interface, meeting their real-time search needs and further enhancing the interactivity of the product search process.

[0052] Furthermore, interactive shelf labels included in the generative object content can be provided not only as buttons but also as text anchors within the content. The generative object content can include text, and the interactive shelf labels can include text anchors embedded within that text. For example, when the generative object content includes text, text anchors can be added to the text. Specifically, anchors can be added to specific text, serving as the entry point for user interaction and triggering corresponding actions. Figure 2 The text content 201 shown may include the anchor text "health goals," which can be used as an interactive shelf label to achieve... Figure 3 The interactive label 311 in 3(a) has the same operational function. The text in the text anchor can be displayed differently from other text, such as by adding an underline to the text in the text anchor. The interactive shelf label in the form of text anchor differs in form from the interactive shelf label in the form of button, but its function can be the same or similar. For example, the interactive shelf label in the form of text anchor can achieve the functions of the aforementioned first interactive label, second interactive label, or third interactive label.

[0053] Interactive shelf labels provided in the user interface may include one or more, and interactive shelf labels of the same type may include one or more. For example, one or more of the aforementioned first interactive label, second interactive label, or third interactive label, or interactive shelf labels in the form of text anchors, may be provided in the user interface. Different interactive shelf labels, such as interactive shelf labels with different functions or different types, may be displayed in different ways to differentiate them visually, for example, they may be rendered as interactive shelf labels with different background colors.

[0054] The above provides a detailed description of a method for providing product information according to embodiments of this application. This method provides a first user interface upon receiving a product information search request; in response to the product information search request, it generates generative object content corresponding to the product information search request based on a pre-trained artificial intelligence model, and displays the generative object content in the first user interface; the generative object content includes product search results and interactive shelf labels; wherein, product search results can be displayed according to a product shelf structure; user operations are received through interactive shelf labels, and corresponding operation actions are performed in response to user operations to refresh or change part or all of the product information search results, or to provide new search content after triggering a new search. This method firstly allows for the generation of generative object content based on a pre-trained artificial intelligence model to provide product search results during product searches. The product information in the search results is included in a product search result structured like a product shelf, presenting rich and structured product search result information, thus improving the richness and readability of the search results. Secondly, the generative object content also includes operable, interactive shelf labels. These labels receive user input and respond to user actions by performing corresponding actions. After an interactive shelf label is manipulated, it generates further actions on the current search results, refreshing or changing part or all of the product search results, or triggering a new search to provide new search content. This satisfies the user's further search interaction needs while browsing the current search results, thereby deepening the granularity of product search needs mining, improving the richness of search results, enhancing the fit between product search results and user needs, and increasing the interactivity of the search process.

[0055] Furthermore, it provides interactive shelf labels of different types and functions. These labels can generate different actions and effects on the current search results in the first user interface. By providing these interactive shelf labels in the search results, users can notice and use the operation options of these labels according to their actual needs during the search results process. This heuristically guides users to obtain search results that better meet their different needs during the product search process, further enriching the content of search results and increasing the interactivity of the product search process.

[0056] Corresponding to the method for providing product information provided in the embodiments of this application, an apparatus for providing product information is also provided, such as... Figure 7 The diagram shown is a schematic representation of a device for providing product information according to an embodiment of this application. The device may include: The interface providing unit 701 is used to receive product information search requests and provide a first user interface; The content providing unit 702 is used to respond to a product information search request, generate generative object content corresponding to the product information search request based on a pre-trained artificial intelligence model, and display the generative object content in a first user interface; the generative object content includes product search results and interactive shelf labels; wherein, the product search results are displayed according to a product shelf structure; The interactive processing unit 703 is used to receive user operations through interactive shelf labels, and to perform corresponding operation actions in response to user operations, so as to refresh or change part or all of the product information search results, or to provide new search content after triggering a new search.

[0057] Interactive shelf labels may include a first interactive label; In this implementation, the interaction processing unit may include: The first interactive processing subunit is used to receive user operations through the first interactive label, respond to the user operations, regenerate the content of the generative object according to the label information corresponding to the first interactive label, and provide the regenerated content of the generative object.

[0058] In another implementation, the interactive shelf label may include a second interactive label; In this implementation, the interaction processing unit may include: The second interactive processing subunit is used to receive user operations through the second interactive label, and in response to the user operations, update the product search results displayed in a product shelf structure according to the label information corresponding to the second interactive label.

[0059] In this implementation, the product search results may also include product information and product category information, wherein one product category information corresponds to one or more product information. The second interactive processing subunit can be used to insert the product category information determined by the tag information corresponding to the second interactive tag into the product category information of the product search results, and provide the corresponding product information under that category.

[0060] In this implementation, the second interactive processing subunit can also be used to provide a retention category operation option for the determined product category information, and when a user operation is received through the retention category operation option, the determined product category information is saved.

[0061] In another implementation, interactive shelf labels may include third interactive labels; In this implementation, the interaction processing unit may include: The third interaction processing subunit is used to receive user operations through the third interaction tag, respond to user operations, provide a second user interface, generate corresponding generative object content according to the tag information corresponding to the third interaction tag, and provide the generative object content generated according to the tag information corresponding to the third interaction tag in the second user interface.

[0062] In this implementation, the product search results include product information and product category information. The generative object content provided in the second user interface includes operation options for product information or operation options for product category information. The third interactive processing subunit can also be used for: Based on whether the user's operation options for product information or product category information result in an operation, the product search results in the first user interface are updated when returning to the first user interface, or the tag information corresponding to the third interaction tag is updated.

[0063] The tag information corresponding to the third interactive tag may include: Based on a product information search request, a divergent prompt question is generated using a pre-trained artificial intelligence model.

[0064] In this device, the product search results may also include product category information, which may include one or any combination of the following product category information: scenario-based product category information; product category-based product category information; recipe-based product category information; and custom product category information.

[0065] In another implementation, the shelf-style structure may include card-type information units; the card-type information units provide a combination of different types of generated content.

[0066] In another implementation, a dialog interaction unit may be provided in the first user interface or the second user interface; The interactive processing unit can also be used to receive new product information search requests through the dialogue interaction unit, and based on the received new product information search requests, regenerate generative object content corresponding to the new product information search requests using a pre-trained artificial intelligence model, and refresh the user interface to provide the regenerated generative object content in the corresponding user interface.

[0067] In another implementation, the generative object content includes text content, and interactive shelf labels may include text anchors within the text content.

[0068] This device can provide a first user interface upon receiving a product information search request; in response to the product information search request, it generates generative object content corresponding to the product information search request based on a pre-trained artificial intelligence model, and displays the generative object content in the first user interface; the generative object content includes product search results and interactive shelf labels; the product search results are displayed according to a product shelf structure; user operations are received through interactive shelf labels, and corresponding operations are performed in response to user operations to refresh or change part or all of the product information search results, or to provide new search content after triggering a new search. This device firstly generates generative object content based on a pre-trained artificial intelligence model to provide product search results during product searches. The product information in the search results is included in a product search result structured like a product shelf, presenting rich and structured product search result information, thus improving the richness and readability of the search results. Secondly, the generative object content also includes operable, interactive shelf labels. These labels receive user input and respond to user actions by performing corresponding actions. After an interactive shelf label is manipulated, it generates further actions on the current search results, refreshing or changing part or all of the product search results, or triggering a new search to provide new search content. This satisfies the user's further search interaction needs while browsing the current search results, thereby deepening the granularity of product search needs mining, improving the richness of search results, enhancing the fit between product search results and user needs, and increasing the interactivity of the search process.

[0069] It should be noted that the embodiments of this application may involve the use of user data. In practical applications, user-specific personal data may be used in the scheme described herein within the scope permitted by applicable laws and regulations, provided that it complies with the applicable laws and regulations of the country (e.g., with the user's explicit consent, with the user being properly notified, etc.).

[0070] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0071] And an electronic device, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any of the foregoing method embodiments.

[0072] A computer program product includes a computer program / computer executable instructions that, when executed by a processor in an electronic device, implement the steps of the method described in the foregoing method embodiments.

[0073] in, Figure 8 The architecture of an electronic device is illustrated by example. For example, device 800 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, aircraft, etc.

[0074] Reference Figure 8 The device 800 may include one or more of the following components: processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input / output (I / O) interface 812, sensor component 814, and communication component 816.

[0075] Processing component 802 typically controls the overall operation of device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods provided in this disclosure. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0076] Memory 804 is configured to store various types of data to support the operation of device 800. Examples of this data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0077] Power supply component 806 provides power to various components of device 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to device 800.

[0078] Multimedia component 808 includes a screen that provides an output interface between device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When device 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0079] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0080] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0081] Sensor assembly 814 includes one or more sensors for providing status assessments of various aspects of device 800. For example, sensor assembly 814 may detect the on / off state of device 800, the relative positioning of components such as the display and keypad of device 800, changes in the position of device 800 or a component of device 800, the presence or absence of user contact with device 800, the orientation or acceleration / deceleration of device 800, and temperature changes of device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0082] Communication component 816 is configured to facilitate wired or wireless communication between device 800 and other devices. Device 800 can access wireless networks based on communication standards, such as WiFi, or mobile communication networks such as 2G, 3G, 4G / LTE, and 5G. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0083] In an exemplary embodiment, device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0084] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of device 800 to perform the method provided by the present disclosure. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0085] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0086] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The systems and system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0087] The foregoing has provided a detailed description of a method and electronic device for providing product information. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of these embodiments are merely for the purpose of helping to understand the method and its core ideas. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for providing product information, characterized in that, include: Receive product information search requests and provide a first user interface; In response to the product information search request, based on a pre-trained artificial intelligence model, generative object content corresponding to the product information search request is generated and displayed in the first user interface; the generative object content includes product search results and interactive shelf labels; wherein, the product search results are displayed according to a product shelf structure; The interactive shelf label receives user input and responds to the user input by performing corresponding actions to refresh or change part or all of the product information search results, or to provide new search content after triggering a new search.

2. The method according to claim 1, characterized in that, The interactive shelf label includes a first interactive label; The step of receiving user input via the interactive shelf label and performing corresponding actions in response to the user input includes: The system receives user actions via the first interactive tag, responds to the user actions, regenerates generative object content based on the tag information corresponding to the first interactive tag, and provides the regenerated generative object content.

3. The method according to claim 1, characterized in that, The interactive shelf label includes a second interactive label; The step of receiving user input via the interactive shelf label and performing corresponding actions in response to the user input includes: The system receives user actions via the second interactive label and, in response to the user actions, updates the product search results displayed in a shelf-like structure based on the label information corresponding to the second interactive label.

4. The method according to claim 3, characterized in that, The product search results include product information and product category information, wherein one product category information corresponds to one or more product information. The step of updating the product search results displayed according to the product shelf structure based on the tag information corresponding to the second interactive tag includes: The product category information determined by the tag information corresponding to the second interactive tag is inserted into the product category information of the product search results, and the corresponding product information is provided under that category.

5. The method according to claim 4, characterized in that, Also includes: The system provides a "Retain Category" option to preserve product category information. When a user operation is received through the "Retain Category" option, the system saves the determined product category information.

6. The method according to claim 1, characterized in that, The interactive shelf label includes a third interactive label; The step of receiving user input via the interactive shelf label and performing corresponding actions in response to the user input includes: The system receives user operations via the third interactive tag, responds to the user operations by providing a second user interface, generates corresponding generative object content based on the tag information corresponding to the third interactive tag, and provides the generative object content generated based on the tag information corresponding to the third interactive tag in the second user interface.

7. The method according to claim 6, characterized in that, The product search results include product information and product category information; the generative object content provided in the second user interface includes operation options for product information or operation options for product category information; The method further includes: Depending on whether the user's operation options for the product information or the operation options for the product category information result in an operation, the product search results in the first user interface are updated when returning to the first user interface, or the tag information corresponding to the third interactive tag is updated.

8. The method according to claim 6, characterized in that, The tag information corresponding to the third interactive tag includes: Based on the product information search request, a divergent prompt question is generated using a pre-trained artificial intelligence model.

9. The method according to claim 1, characterized in that, The product search results include product category information, which includes one or any combination of the following product category information: Scenario-based product category information; Product category classification information; Recipe category information; Customize product category information.

10. The method according to claim 1, characterized in that, The product shelf structure includes card-type information units; The method further includes: The card-type information unit provides a combination of different types of generated content.

11. The method according to claim 6, characterized in that, Also includes: A dialog interaction unit is provided in the first user interface or the second user interface; The dialogue interaction unit receives new product information search requests, and based on the received new product information search requests, regenerates generative object content corresponding to the new product information search requests using a pre-trained artificial intelligence model, and refreshes the user interface to provide the regenerated generative object content in the corresponding user interface.

12. The method according to any one of claims 1-11, characterized in that, The generative object content includes text content; the interactive shelf label includes text anchors in the text content.

13. An electronic device, characterized in that, include: One or more processors; as well as A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method according to any one of claims 1 to 12.

Images